By ID

Concept

This version uses the sample number and barcode ID to choose human cells from an initial clustering of all data to the mixed human/mouse reference genomes. With this vector of IDs, a python script finds corresponding fastq read identifiers (since only the bam file contains “corrected” barcodes). The script then iterates through the paired fastq file, partitioning the matching (human) and non-matching (mouse) reads to separate fastq pairs. These are then run though cellranger count using only the appropriate genomes.

Load human genome split of samples, labeling with hs1..hs4. Output matrix.
Convert to common mouse genes. Re-load into object. Load mouse genome split of samples, labeling with ms1..ms4. Subset overlapping genes. Merge all 8. Normalize and scale. Show clusters labeled by cell; split by sample. Show nCount_RNA also. Determine significantly-different list mouse vs human.

hs1.data=Read10X(data.dir="./hg19/S1/outs/filtered_feature_bc_matrix/")
hs2.data=Read10X(data.dir="./hg19/S2/outs/filtered_feature_bc_matrix/")
hs3.data=Read10X(data.dir="./hg19/S3/outs/filtered_feature_bc_matrix/")
hs4.data=Read10X(data.dir="./hg19/S4/outs/filtered_feature_bc_matrix/")
ms1.data=Read10X(data.dir="./mm10/S1/outs/filtered_feature_bc_matrix/")
ms2.data=Read10X(data.dir="./mm10/S2/outs/filtered_feature_bc_matrix/")
ms3.data=Read10X(data.dir="./mm10/S3/outs/filtered_feature_bc_matrix/")
ms4.data=Read10X(data.dir="./mm10/S4/outs/filtered_feature_bc_matrix/")

#some human gene symbols have underscores (but these are not in geneTrans).
#Substitute a dot so as not to raise an error.
rownames(hs1.data)=gsub("_",".",rownames(hs1.data))
rownames(hs2.data)=gsub("_",".",rownames(hs2.data))
rownames(hs3.data)=gsub("_",".",rownames(hs3.data))
rownames(hs4.data)=gsub("_",".",rownames(hs4.data))

#rename cells
colnames(x=hs1.data) <- paste('hs1',colnames(x=hs1.data),sep="_")
colnames(x=hs2.data) <- paste('hs2',colnames(x=hs2.data),sep="_")
colnames(x=hs3.data) <- paste('hs3',colnames(x=hs3.data),sep="_")
colnames(x=hs4.data) <- paste('hs4',colnames(x=hs4.data),sep="_")
colnames(x=ms1.data) <- paste('ms1',colnames(x=ms1.data),sep="_")
colnames(x=ms2.data) <- paste('ms2',colnames(x=ms2.data),sep="_")
colnames(x=ms3.data) <- paste('ms3',colnames(x=ms3.data),sep="_")
colnames(x=ms4.data) <- paste('ms4',colnames(x=ms4.data),sep="_")

#create objects
hs1=CreateSeuratObject(counts=hs1.data,project="MG",min.cells=5)
hs2=CreateSeuratObject(counts=hs2.data,project="MG",min.cells=5)
hs3=CreateSeuratObject(counts=hs3.data,project="MG",min.cells=5)
hs4=CreateSeuratObject(counts=hs4.data,project="MG",min.cells=5)
ms1=CreateSeuratObject(counts=ms1.data,project="MG",min.cells=5)
ms2=CreateSeuratObject(counts=ms2.data,project="MG",min.cells=5)
ms3=CreateSeuratObject(counts=ms3.data,project="MG",min.cells=5)
ms4=CreateSeuratObject(counts=ms4.data,project="MG",min.cells=5)

#Follow https://satijalab.org/seurat/essential_commands.html 
hg=merge(x=hs1,y=c(hs2,hs3,hs4),project="Hg")
mg=merge(x=ms1,y=c(ms2,ms3,ms4),project="Mg")

#at this point we don't need all the original sample objects--can re-create if needed
rm(hs1,hs2,hs3,hs4,hs1.data,hs2.data,hs3.data,hs4.data)
rm(ms1,ms2,ms3,ms4,ms1.data,ms2.data,ms3.data,ms4.data)

#summary of each object
print(hg)

## An object of class Seurat 
## 10930 features across 1683 samples within 1 assay 
## Active assay: RNA (10930 features)

print(mg)

## An object of class Seurat 
## 17264 features across 28218 samples within 1 assay 
## Active assay: RNA (17264 features)

Convert human genes to mouse

Output raw data to data frame. Use conversion table (geneTrans) to translate human symbols to mouse symbols.

#load gene translation table
geneTrans=read.table("geneTrans.txt",sep=",",header=T,stringsAsFactors = F,row.names = 1)

mito.m=grep("^mt",rownames(mg),value=T)
mito.h=grep("^MT-",rownames(hg),value=T)
#turns out, these two vectors (n=13 each) are ordered and match, build an extended translation table
mitoTrans=data.frame(row.names = paste("mm10",mito.m,sep="_"),
                     Human.Symbol = mito.h,
                     Homologene_ID = rep(NA,13),
                     None = rep("yes",13),
                     Mouse.Symbol = mito.m,
                     hg19 = paste("hg19",mito.h,sep="_"),
                     mm10 = paste("mm10",mito.m,sep="_")
                     )

#extended translation table
xTrans = rbind(geneTrans,mitoTrans)

#extract human raw counts into table
hg.raw=GetAssayData(hg,slot="counts")

#subset rows in geneTrans (not necessary but simpler)
hg.raw=hg.raw[row.names(hg.raw) %in% xTrans$Human.Symbol,]  #cut from 13283 to 11364 rows

#translate human symbols to mouse
hg.trans=merge(x=hg.raw,y=xTrans[,c(1,4)],by.x=0,by.y="Human.Symbol",all.x=T)
rownames(hg.trans)=hg.trans$Mouse.Symbol
hg.trans=hg.trans[,!(names(hg.trans) %in% c("Row.names","Mouse.Symbol"))]

#extract mouse raw counts
mg.raw=GetAssayData(mg,slot="counts")

#subset mouse rows in xTrans only
mg.raw=mg.raw[row.names(mg.raw) %in% xTrans$Mouse.Symbol,]

#convert both matrices back into Seurat objects
hm=CreateSeuratObject(hg.trans,project="MG",min.cells=5)
mg=CreateSeuratObject(mg.raw,project="MG",min.cells=5)

print(hm)

## An object of class Seurat 
## 9336 features across 1683 samples within 1 assay 
## Active assay: RNA (9336 features)

print(mg)

## An object of class Seurat 
## 14526 features across 28218 samples within 1 assay 
## Active assay: RNA (14526 features)

Merge objects

hm=merge(x=hm,y=mg,project="HM")

#clean up objects no longer needed
rm(hg,mg,hg.raw,mito.m,mito.h)

#summarize merged object
print(hm)

## An object of class Seurat 
## 14725 features across 29901 samples within 1 assay 
## Active assay: RNA (14725 features)

Scale and normalize

Use standard workflow to calculate percent.mito (now all mouse symbols) and visualize by sample.

#filter and normalize merged object
mito.features=grep(pattern="^mt",x=rownames(x=hm),value=T)

percent.mito=Matrix::colSums(x=GetAssayData(object=hm,slot="counts")[mito.features,]) / Matrix::colSums(x=GetAssayData(object=hm,slot='counts'))
hm[['percent.mito']] = percent.mito

Diagnostic plots.

VlnPlot(object=hm,features=c("nFeature_RNA","nCount_RNA","percent.mito"),ncol=3)

FeatureScatter(object=hm,feature1 = "nCount_RNA",feature2 = "percent.mito")

FeatureScatter(object=hm,feature1 = "nCount_RNA",feature2 = "nFeature_RNA")

Scale

Print summary data before and after subsetting. Then normalize, find variable genes, and scale.

print(hm)

## An object of class Seurat 
## 14725 features across 29901 samples within 1 assay 
## Active assay: RNA (14725 features)

hm=subset(hm,nFeature_RNA > 200 & nFeature_RNA < 2500 & percent.mito < 0.05) #try > 100 & < 2500 & < .5
print(hm)

## An object of class Seurat 
## 14725 features across 8980 samples within 1 assay 
## Active assay: RNA (14725 features)

hm=NormalizeData(hm,normalization.method = "LogNormalize",scale.factor=1e4)
hm=FindVariableFeatures(hm,selection.method = 'mean.var.plot',mean.cutoff = c(0.0125,3),dispersion.cutoff = c(0.5,Inf)) #finds 4047 features
length(VariableFeatures(hm))

## [1] 2105

hm=ScaleData(hm,features=rownames(hm),vars.to.regress = c("nCount_RNA","percent.mito"))  #this takes a while

## Regressing out nCount_RNA, percent.mito

## Scaling data matrix

Dimension reduction

Start with PCA and determine how many dimensions are informative.

hm=RunPCA(hm,features=VariableFeatures(hm),verbose=T)

## PC_ 1 
## Positive:  C1qb, C1qa, C1qc, B2m, Cx3cr1, Cd74, Fcer1g, Rpl13a, Lst1, Gpr34 
##     Spp1, Trem2, Uba52, Sat1, Apoc1, Cybb, Alox5ap, Rpl29, H2-Ea-ps, Rnaset2a 
##     Ptprc, Maf, C3, Ctss, Fos, Fcgr4, P2ry13, P2ry12, Olfml3, Cd84 
## Negative:  Gria2, Ptn, Meg3, Tsc22d1, Spock2, Pcp4l1, Crip2, Ahi1, Flt1, Meis2 
##     Nrxn3, Epha5, Cldn5, Igfbp7, Itm2a, Id3, Id1, Syt1, Snap25, Grin2b 
##     Sorbs2, Igf1r, Scg5, Epas1, Stmn3, Il1rapl1, Snhg11, Fry, R3hdm1, Ablim1 
## PC_ 2 
## Positive:  Flt1, Cldn5, Itm2a, Igfbp7, Ptprb, Id1, Abcb1a, Pglyrp1, Klf2, Egfl7 
##     Cxcl12, Adgrf5, Slc2a1, Fn1, Ramp2, Sox18, Ablim1, Adgrl4, Ahnak, Sgms1 
##     Jcad, Esam, Epas1, Spock2, Pecam1, Abcg2, Pltp, Crip1, Kitl, Slc9a3r2 
## Negative:  Gria2, Meg3, Meis2, Syt1, Nrxn3, Atp1b1, Il1rapl1, Epha5, Grin2b, Celf4 
##     Ahi1, Stmn3, Snap25, Scg5, Negr1, Ndrg4, Rtn1, Ncam1, Snhg11, Plppr4 
##     Arpp21, Bex2, Ank3, Peg3, Gad1, Synpr, Opcml, Pcsk2, Eml5, Mt3 
## PC_ 3 
## Positive:  Syt1, Meg3, Snap25, Ndrg4, Celf4, Gad1, Snhg11, Camk2b, Plppr4, Synpr 
##     Atp2b1, Stmn3, Atp1a3, Ano3, Grin2b, Nrip3, Pcp4l1, Eml5, Bcl11a, Snca 
##     Gad2, Pcp4, C1qtnf4, Myt1l, Ccsap, Pcsk2, Nrxn3, Grin2a, Sipa1l1, Syt6 
## Negative:  Atp1a2, Slc1a2, Clu, Gpr37l1, Mt2, F3, Cldn10, Mt3, Ptn, Cxcl14 
##     Rorb, Slc7a10, Gjb6, Fxyd1, Tril, Aqp4, Fgfr3, Hes5, Slc6a11, Pla2g7 
##     Msmo1, Tmem47, Vegfa, Appl2, Fjx1, Gabrb1, Mlc1, Phkg1, Car2, Etnppl 
## PC_ 4 
## Positive:  Hexb, Ctss, Ctsd, Fyb, Rnase4, Vsir, Tmem119, Lgmn, Selplg, Fcgr3 
##     Cd52, Ctsz, Cx3cr1, Mafb, C1qa, C1qc, Unc93b1, P2ry12, Tgfbr1, Ptpn18 
##     Arsb, Itgb5, Ssh2, Rhoh, Fcer1g, P2ry6, Man2b1, Arhgap45, C1qb, Pou2f2 
## Negative:  Spp1, Cd74, H2-Ea-ps, C3, Apoc1, Cybb, Tpm1, A2m, Neat1, S100a11 
##     Fcgr4, Ifi203, Arl5a, H2-DMb1, Rpl29, H2-Eb1, Olr1, 1500009L16Rik, H2-Bl, Folr2 
##     Sorl1, Rpl13a, Lilrb4a, Glipr1, Adam28, Fcgrt, Uba52, Atm, Clec7a, Tgoln2 
## PC_ 5 
## Positive:  Mt3, Slc1a2, Mt2, Atp1a2, Clu, Cxcl14, Cldn10, F3, Gpr37l1, Gria2 
##     Rorb, Pla2g7, Gjb6, Gabrb1, Slc7a10, Aqp4, Slc6a11, Fgfr3, Fjx1, Tril 
##     Tmem47, Fxyd1, Mlc1, Hes5, Appl2, Tubb2b, Phkg1, Etnppl, Vegfa, Fut9 
## Negative:  Cldn11, Ermn, Tspan2, Mog, Tubb4a, Ugt8a, Mag, Ppp1r14a, Tmem88b, Cnp 
##     Opalin, Mal, Nkx6-2, Stmn4, Qdpr, Mobp, Cryab, Kctd13, Gjc3, Grb14 
##     Anln, Sept4, Hapln2, Ttll7, Enpp2, Efnb3, Slc24a2, Tmeff2, Edil3, Kcna1

print(hm[['pca']],dims=1:5,nfeatures=5,projected=F)

## PC_ 1 
## Positive:  C1qb, C1qa, C1qc, B2m, Cx3cr1 
## Negative:  Gria2, Ptn, Meg3, Tsc22d1, Spock2 
## PC_ 2 
## Positive:  Flt1, Cldn5, Itm2a, Igfbp7, Ptprb 
## Negative:  Gria2, Meg3, Meis2, Syt1, Nrxn3 
## PC_ 3 
## Positive:  Syt1, Meg3, Snap25, Ndrg4, Celf4 
## Negative:  Atp1a2, Slc1a2, Clu, Gpr37l1, Mt2 
## PC_ 4 
## Positive:  Hexb, Ctss, Ctsd, Fyb, Rnase4 
## Negative:  Spp1, Cd74, H2-Ea-ps, C3, Apoc1 
## PC_ 5 
## Positive:  Mt3, Slc1a2, Mt2, Atp1a2, Clu 
## Negative:  Cldn11, Ermn, Tspan2, Mog, Tubb4a

VizDimLoadings(hm,dims=1:2)

DimPlot(hm)

hm=ProjectDim(hm)

## PC_ 1 
## Positive:  Tyrobp, C1qb, C1qa, C1qc, Aif1, B2m, Cx3cr1, Laptm5, Cd74, Fcer1g 
##     Rpl13a, Lst1, Gpr34, Ftl1, Cyba, Spp1, Trem2, Uba52, Csf1r, Sat1 
## Negative:  Gria2, Ptn, Sptbn1, Meg3, Selenow, Tsc22d1, Zbtb20, Tcf4, mt-Atp6, Bsg 
##     Mt1, Pcsk1n, Nfib, Spock2, Pbx1, Atp5j, Selenom, Pcp4l1, Elob, Xist 
## PC_ 2 
## Positive:  Flt1, Cldn5, Itm2a, Igfbp7, Ptprb, Id1, Abcb1a, Pglyrp1, Klf2, Egfl7 
##     Cxcl12, Adgrf5, Slc2a1, Bsg, Fn1, Ramp2, Sox18, Ablim1, Adgrl4, Ahnak 
## Negative:  Gria2, Ckb, Meg3, Meis2, Dclk1, Ank2, Pcsk1n, Syt1, Nrxn3, Atp1b1 
##     Il1rapl1, Epha5, Grin2b, Nrxn1, Dlgap1, Celf2, Celf4, Ahi1, Cadm2, Stmn3 
## PC_ 3 
## Positive:  Syt1, Meg3, Snap25, Ndrg4, Mef2c, Celf4, Gad1, Snhg11, Calm2, Camk2b 
##     Plppr4, Synpr, Atp2b1, Tmsb4x, Stmn3, Atp1a3, Tmsb10, Ano3, Grin2b, Rps19 
## Negative:  Atp1a2, Plpp3, Aldoc, Gja1, Slc1a2, Prdx6, Ntsr2, Slc1a3, Clu, Mt1 
##     Gpr37l1, Mt2, Mfge8, F3, Sparcl1, Atp1b2, Glul, Ptprz1, Id4, Cldn10 
## PC_ 4 
## Positive:  Hexb, Ctss, Ctsd, Fyb, Rnase4, Vsir, Tmem119, Lgmn, Selplg, Fcgr3 
##     Rpl17, Cd52, Rps17, Ctsz, Serinc3, Sparc, Cx3cr1, Csf1r, Mafb, Cst3 
## Negative:  Spp1, Cd74, H2-Ea-ps, C3, Apoc1, Cybb, Tpm1, A2m, Neat1, S100a11 
##     Fcgr4, Ifi203, Arl5a, H2-DMb1, Rpl29, H2-Eb1, Olr1, 1500009L16Rik, H2-Bl, Folr2 
## PC_ 5 
## Positive:  Gja1, Mt3, Slc1a2, Mt2, Aldoc, Atp1a2, S1pr1, Clu, Ntsr2, Cst3 
##     Sparcl1, Slc1a3, Plpp3, Atp1b2, Cxcl14, Dclk1, Id4, Prdx6, Chchd10, Ntm 
## Negative:  Cldn11, Ermn, Tspan2, Mog, Tubb4a, Ugt8a, Plp1, Mag, Ppp1r14a, Tmem88b 
##     Cnp, Opalin, Mal, Nkx6-2, Stmn4, Qdpr, Mobp, Cryab, Kctd13, Gjc3

DimHeatmap(hm,dims=1,cells=500,balanced=T)

DimHeatmap(hm,dims=1:6,cells=500,balanced=T)

hm=JackStraw(hm,num.replicate=100)
hm=ScoreJackStraw(hm,dims=1:20)
JackStrawPlot(hm,dims=1:20)

## Warning: Removed 29460 rows containing missing values (geom_point).

ElbowPlot(hm)

Start clustering

#start clustering
hm=FindNeighbors(hm,dims=1:13) #adjust dims based on plots

## Computing nearest neighbor graph

## Computing SNN

hm=FindClusters(hm,resolution=0.2)

## Modularity Optimizer version 1.3.0 by Ludo Waltman and Nees Jan van Eck
## 
## Number of nodes: 8980
## Number of edges: 313442
## 
## Running Louvain algorithm...
## Maximum modularity in 10 random starts: 0.9679
## Number of communities: 12
## Elapsed time: 1 seconds

table(Idents(hm))

## 
##    0    1    2    3    4    5    6    7    8    9   10   11 
## 2188 1579 1334 1048  542  481  477  427  385  273  201   45

Find tSNE projection and add to object

hm=RunTSNE(hm,dims=1:13)
DimPlot(hm,reduction='tsne')

DimPlot(hm,reduction='tsne',split.by='orig.ident')

FeaturePlot(hm,features='Spp1')

FeaturePlot(hm,features='Hexb')

FeaturePlot(hm,features='nCount_RNA')

UMAP

hm=RunUMAP(hm,dims = 1:13)
DimPlot(hm,reduction='umap')

FeaturePlot(hm,features='Spp1')

FeaturePlot(hm,features='Hexb')

#FeaturePlot(hm,features='nCount_RNA',split.by='orig.ident')
FeaturePlot(hm,features='nCount_RNA')

Label clusters

Use top 2 genes from prior clustering to do this, following

hm.markers=FindAllMarkers(hm,only.pos=T,min.pct = .25,logfc.threshold = .25)

## Calculating cluster 0

## Calculating cluster 1

## Calculating cluster 2

## Calculating cluster 3

## Calculating cluster 4

## Calculating cluster 5

## Calculating cluster 6

## Calculating cluster 7

## Calculating cluster 8

## Calculating cluster 9

## Calculating cluster 10

## Calculating cluster 11

hm.markers %>% group_by(cluster) %>% top_n(10,avg_logFC)

## # A tibble: 120 x 7
## # Groups:   cluster [12]
##    p_val avg_logFC pct.1 pct.2 p_val_adj cluster gene  
##    <dbl>     <dbl> <dbl> <dbl>     <dbl> <fct>   <chr> 
##  1     0      2.70 0.987 0.234         0 0       Slc1a2
##  2     0      2.53 0.949 0.137         0 0       Aldoc 
##  3     0      2.40 0.973 0.265         0 0       Mt2   
##  4     0      2.39 0.941 0.127         0 0       Plpp3 
##  5     0      2.36 0.889 0.107         0 0       Clu   
##  6     0      2.35 0.986 0.322         0 0       Mt3   
##  7     0      2.32 0.936 0.106         0 0       Gja1  
##  8     0      2.29 0.851 0.071         0 0       Ntsr2 
##  9     0      2.28 0.995 0.531         0 0       Mt1   
## 10     0      2.20 0.975 0.288         0 0       Slc1a3
## # … with 110 more rows

Save top 5 list

hm.markers %>% group_by(cluster) %>% top_n(5,avg_logFC) %>% write.csv("ID Top 5 per cluster.csv",row.names = F)
hm.markers %>% group_by(cluster) %>% top_n(5,avg_logFC) %>% as.data.frame %>% paged_table

Identify human and mouse microglial clusters

Use Spp1 and Hexb to identify cluster number for human and mouse microglia, respectively.

humClus=as.character(subset(hm.markers,gene=="Spp1")$cluster)
print(humClus)

## [1] "2"

musClus=as.character(subset(hm.markers,gene=="Hexb")$cluster)
print(musClus)

## [1] "1"  "11"

Find genes differentially expressed between human and mouse microglia

diffGenes=FindMarkers(hm,ident.1=humClus,ident.2=musClus,min.pct=0.1)

Display summary of differentiall expressed genes

table(sig=diffGenes$p_val_adj <= 0.05, twofold=abs(diffGenes$avg_logFC) >= 1)

##        twofold
## sig     FALSE TRUE
##   FALSE    20    0
##   TRUE   1428  217

diffGenes %>% tibble::rownames_to_column() %>% filter(p_val_adj <= 0.05) %>% filter(abs(avg_logFC) >= 1) %>% paged_table

Save differential expressed list as object (for later use in R) and csv (as text to preserve gene names)

saveRDS(diffGenes,"by_id_diffGenes.rds")
write.table(as.data.frame(diffGenes),"ID_diffGenes_csv.txt",sep=",",quote=T)

Cluster Averages

hm.mean=AverageExpression(hm)

## Finished averaging RNA for cluster 0

## Finished averaging RNA for cluster 1

## Finished averaging RNA for cluster 2

## Finished averaging RNA for cluster 3

## Finished averaging RNA for cluster 4

## Finished averaging RNA for cluster 5

## Finished averaging RNA for cluster 6

## Finished averaging RNA for cluster 7

## Finished averaging RNA for cluster 8

## Finished averaging RNA for cluster 9

## Finished averaging RNA for cluster 10

## Finished averaging RNA for cluster 11

head(hm.mean$RNA)

##                0           1          2           3           4          5
## A1bg  0.00000000 0.000000000 0.65321979 0.000000000 0.000000000 0.00000000
## A2m   0.07496938 0.005165434 5.83612846 0.005529554 0.024180524 0.03200524
## Aaas  0.03003902 0.051494882 0.09339857 0.090743325 0.004724759 0.09316861
## Aacs  0.21218134 0.047823888 0.04391915 0.052250458 0.075924614 0.04550186
## Aagab 0.09828363 0.282612763 0.06032349 0.120720215 0.157264117 0.12593642
## Aak1  0.56055607 0.296952853 2.20932446 0.496353622 1.334404149 0.31267420
##                6          7          8          9         10         11
## A1bg  0.00000000 0.00000000 0.00000000 0.00000000 0.00000000 0.00000000
## A2m   0.01135664 0.02531972 0.30322714 0.03518736 0.03389049 0.06655353
## Aaas  0.04748904 0.03711213 0.09451190 0.05990435 0.03999296 0.08755801
## Aacs  0.05189994 0.00000000 0.01515292 0.00000000 0.13366719 0.00000000
## Aagab 0.09408680 0.07424196 0.11395543 0.03192328 0.05093002 0.00000000
## Aak1  0.78728846 1.48532449 0.42730432 0.41475770 0.73986350 0.66761264

write.csv(hm.mean$RNA,"ID_hm_cluster_averages_csv.txt")

Show species by original split

#stash idents 
hm[["old.ident"]]=Idents(hm)
#get vector of cell idents
all.cells=Cells(hm)
#split by species
hg.cells=grep("^h",all.cells,value=T)
mm.cells=grep("^m",all.cells,value=T)
#apply new idents
Idents(hm,cells=hg.cells)="Human"
Idents(hm,cells=mm.cells)="Mouse"
table(hm$orig.ident,Idents(hm))

##      
##       Mouse Human
##   hs1     0   317
##   hs2     0   232
##   hs3     0   510
##   hs4     0   307
##   ms1  1684     0
##   ms2   729     0
##   ms3  3273     0
##   ms4  1928     0

Plot tsne labeled by species no legend

DimPlot(hm,label=T,repel=T,label.size=8,reduction = "tsne")+NoLegend()

Plot nCounts in tsne labeled by species

FeaturePlot(hm,features='nCount_RNA',reduction = "tsne")

FeaturePlot(hm,features='nCount_RNA',reduction = "tsne",split.by="ident")

Check overlapping cells

Distribution of detected transcripts

To test the level of detection in each cell, we’ll display the distribution of counted transcripts per cells.

#replace counts > 0 with T/F
hg.nz=as.data.frame(hg.trans) > 0
mg.nz=as.data.frame(mg.raw) > 0

#sum the TRUE values for each column (cell)
mg.nz=apply(mg.nz,MARGIN=2,FUN=sum)
hg.nz=apply(hg.nz,MARGIN=2,FUN=sum)

#check distributions
plot(density(log10(hg.nz)))
lines(density(log10(mg.nz)),lty="dashed")

Venn

Finally, we’ll check whether any cell identifiers (sample_barcode) are found in common across the two species.

#Venn
#extract only sample_barcodes with more than 500 genes > 0
hg.x=names(which(hg.nz > 500))
mg.x=names(which(mg.nz > 500))


#strip off species code from sample index and assemble into list
#diffList=list(hg19=sapply(strsplit(hg.x,"_"),`[`,2),mm10=sapply(strsplit(mg.x,"_"),`[`,2))
diffList=list(hg19=unique(sub("h","",hg.x)),mm10=unique(sub("m","",mg.x)))
#generate object
venn.plot=venn.diagram(diffList,filename=NULL,euler.d=T,scaled=T,col='transparent',
                       alpha=.5,fill=c("cornflowerblue","coral2"),
                       fontfamily='Helvetica',cat.fontfamily='Helvetica',cat.cex=3,cex=2)
png("ID Venn Overlap.png",width=1200,height=900)
grid.draw(venn.plot) #save to file
dev.off()

## png 
##   2

grid.newpage()
#plot it in output
grid.draw(venn.plot)

Session Info

sessionInfo()

## R version 3.5.3 (2019-03-11)
## Platform: x86_64-pc-linux-gnu (64-bit)
## Running under: Ubuntu 18.04.2 LTS
## 
## Matrix products: default
## BLAS: /usr/lib/x86_64-linux-gnu/atlas/libblas.so.3.10.3
## LAPACK: /usr/lib/x86_64-linux-gnu/atlas/liblapack.so.3.10.3
## 
## locale:
##  [1] LC_CTYPE=en_US.UTF-8       LC_NUMERIC=C              
##  [3] LC_TIME=en_US.UTF-8        LC_COLLATE=en_US.UTF-8    
##  [5] LC_MONETARY=en_US.UTF-8    LC_MESSAGES=en_US.UTF-8   
##  [7] LC_PAPER=en_US.UTF-8       LC_NAME=C                 
##  [9] LC_ADDRESS=C               LC_TELEPHONE=C            
## [11] LC_MEASUREMENT=en_US.UTF-8 LC_IDENTIFICATION=C       
## 
## attached base packages:
## [1] grid      stats     graphics  grDevices utils     datasets  methods  
## [8] base     
## 
## other attached packages:
## [1] VennDiagram_1.6.20  futile.logger_1.4.3 rmarkdown_1.12     
## [4] dplyr_0.8.0.1       Seurat_3.0.0.9000  
## 
## loaded via a namespace (and not attached):
##  [1] nlme_3.1-137         tsne_0.1-3           bitops_1.0-6        
##  [4] RColorBrewer_1.1-2   httr_1.4.0           tools_3.5.3         
##  [7] utf8_1.1.4           R6_2.4.0             irlba_2.3.3         
## [10] KernSmooth_2.23-15   lazyeval_0.2.2       colorspace_1.4-1    
## [13] withr_2.1.2          npsurv_0.4-0         tidyselect_0.2.5    
## [16] compiler_3.5.3       cli_1.1.0            formatR_1.6         
## [19] plotly_4.9.0         labeling_0.3         caTools_1.17.1.2    
## [22] scales_1.0.0         lmtest_0.9-36        ggridges_0.5.1      
## [25] pbapply_1.4-0        stringr_1.4.0        digest_0.6.18       
## [28] R.utils_2.8.0        pkgconfig_2.0.2      htmltools_0.3.6     
## [31] bibtex_0.4.2         htmlwidgets_1.3      rlang_0.3.4         
## [34] zoo_1.8-5            jsonlite_1.6         ica_1.0-2           
## [37] gtools_3.8.1         R.oo_1.22.0          magrittr_1.5        
## [40] Matrix_1.2-17        fansi_0.4.0          Rcpp_1.0.1          
## [43] munsell_0.5.0        ape_5.3              reticulate_1.12     
## [46] R.methodsS3_1.7.1    stringi_1.4.3        yaml_2.2.0          
## [49] gbRd_0.4-11          MASS_7.3-51.1        gplots_3.0.1.1      
## [52] Rtsne_0.15           plyr_1.8.4           parallel_3.5.3      
## [55] gdata_2.18.0         listenv_0.7.0        ggrepel_0.8.0       
## [58] crayon_1.3.4         lattice_0.20-38      cowplot_0.9.4       
## [61] splines_3.5.3        SDMTools_1.1-221     knitr_1.22          
## [64] pillar_1.3.1         igraph_1.2.4         future.apply_1.2.0  
## [67] codetools_0.2-16     futile.options_1.0.1 glue_1.3.1          
## [70] evaluate_0.13        lsei_1.2-0           metap_1.1           
## [73] lambda.r_1.2.3       data.table_1.12.2    png_0.1-7           
## [76] Rdpack_0.11-0        gtable_0.3.0         RANN_2.6.1          
## [79] purrr_0.3.2          tidyr_0.8.3          future_1.12.0       
## [82] assertthat_0.2.1     ggplot2_3.1.1        xfun_0.6            
## [85] rsvd_1.0.0           survival_2.43-3      viridisLite_0.3.0   
## [88] tibble_2.1.1         cluster_2.0.8        globals_0.12.4      
## [91] fitdistrplus_1.0-14  ROCR_1.0-7